智能AI None AdamW 训练动态下的威布尔体重尺度参数演化 arXiv:2606.19367v1 Announce Type: new Abstract: Building on a two-parameter Weibull framework for diagnosing transformer the and weight 2026-06-19 Tiexin Ding
智能AI None 体重标准设定了摸索时间尺度：因果延迟定律 13753v1 Announce Type: new Abstract: Grokking is the delayed onset of generalization in neural networks, arising long af the norm delay 2026-06-15 Truong Xuan Khanh, Doan Hoang Viet, Luu Duc Trung, Phan Thanh Duc
开源推荐 None GitHub 热门项目: llama3-from-scratch GitHub项目：llama3-from-scratch 仓库地址：https://github。 weight layers llama 2026-05-25 GitHub Trending